Search Results (1,150)

Accurate fruit counting is crucial for data-driven decision-making in modern precision agriculture. In strawberry cultivation, a labor-intensive sector, automated, scalable yield estimation is especially critical. However, dense foliage, variable lighting, visual ambiguity of ripeness stages, and fruit clustering pose significant challenges. To overcome these, we developed a real-time multi-stage framework for strawberry detection and counting by optimizing a YOLOv8s detector and integrating a class-aware tracking system. The detector was enhanced with a lightweight C3x module, an additional detection head for small objects, and the Wise-IOU (WIoU) loss function, thereby improving performance against occlusion. Our final model achieved a 92.5% mAP@0.5, outperforming the baseline while reducing the number of parameters by 27.9%. This detector was integrated with the ByteTrack multiple object tracking (MOT) algorithm. Our system enabled accurate, automated fruit counting in complex greenhouse environments. When validated on video data, results showed a strong correlation with ground-truth counts (R² = 0.914) and a low mean absolute percentage error (MAPE) of 9.52%. Counting accuracy was highest for ripe strawberries (R² = 0.950), confirming the value for harvest-ready estimation. This work delivers an efficient, accurate, and resource-conscious solution for automated yield monitoring in commercial strawberry production. Full article

Background: Tularemia is a rarely identified disease in Slovenia. In summer 2024, we detected a tularemia outbreak in the Kranjsko-Sorško polje, located in North-Western part of Slovenia. Aim: To describe the epidemiological investigations and preventive measures to contain the outbreak. Methods: The patients with confirmed tularemia were interviewed. Serology and PCR was used for microbiological confirmation of tularemia and in some patients by isolation from blood or by RT-PCR. Results: The majority of confirmed tularemia cases in 2024 were infected in the geographically limited area in North-Western part of Slovenia (38/46). Tularemia was confirmed in two patients by isolation Francisella tularensis subsp. holarctica from blood or wound, in one by blood PCR, and in the others by serology. Most cases were associated with mowing or harvesting hay with intensive dusting. Twenty-eight (75.7%) out of 37 cases developed pulmonary tularemia. Sixteen cases were hospitalized. After confirming the outbreak, we alerted medical professionals in the region and the general public using the regional and national media and website of National Institute of Public Health. Conclusions: Endemic tularemia in Slovenia is associated with handling wild life and presents in ulceroglandular form. In the localized outbreak in year 2024 there was an extraordinary upsurge of pulmonary tularemia, with many of the cases initially investigated for lung cancer based on the radiology reports. Due to dry weather condition in summer 2024, excessive dusting associated with mowing the grass and handling hay resulted in inhalation of infective aerosols leading to the infection with F. tularensis. Full article

Watermelon is a popular fruit, predominantly cultivated in Asian countries. However, the production and harvesting processes present several challenges. Due to its size and weight, manually harvesting watermelons is labor-intensive and costly. In the future, technology is expected to enable robots to harvest watermelons. Therefore, it becomes essential to introduce intelligent systems to effectively identify and locate watermelons in harvesting. This research aims to develop an advanced methodology for watermelon identification and location using You Look Only Once (YOLO)v8 and YOLOv8-oriented bounding box (OBB) algorithms. Furthermore, the simple online and real-time tracking (SORT) algorithm was employed to track and count watermelons and estimate yield. The performance of YOLOv8-OBB was better than that of YOLOv8 and the highest precision (0.938) was achieved by YOLOv8s-OBB. Additionally, the size of each watermelon was measured with both models. The models help farmers find the optimal watermelons for harvest. Full article

Livestock-intensive regions in Europe face dual challenges: nutrient surpluses and a high dependency on import of high-protein feedstocks. This study proposes duckweed (Lemnaceae) as a potential solution by recovering nutrients from manure-derived waste streams while producing protein-rich biomass. This study evaluated the performance of duckweed treatment systems at a pig manure processing facility in Belgium. Three outdoor systems were monitored over a full growing season under temperate climate conditions. Duckweed cultivated on constructed wetland effluent showed die-off and low protein content, while systems supplied with diluted liquid fraction and nitrification–denitrification effluent achieved consistent growth, yielding 8 tonnes of dry biomass/ha/year and 2.8 tonnes of protein/ha/year. Average removal rates were 1.2 g N/m²/day and 0.13 g P/m²/day. Growth ceased after approximately 100–120 days, likely due to rising pH and electrical conductivity, suggesting ammonia toxicity and salt stress. Harvested duckweed had a high protein content and a total amino acid profile suitable for broilers, though potentially limiting in histidine and methionine for pigs or cattle. Additionally, promising energy and protein values for ruminants were measured. Although high ash and fibre contents may limit use in monogastric animals, duckweed remains suitable as part of a balanced feed. Its broad mineral profile further supports its use as a circular, locally sourced feed supplement. Full article

Erythrina edulis, commonly known as pajuro, is a large leguminous plant native to the Amazon region of Peru. Its seeds are valued for their high protein content and their potential to enhance food security in rural communities. However, the current methods of harvesting and sorting are entirely manual, making the process labor-intensive, time-consuming, and subject to high variability, particularly in industrial contexts. A custom lightweight convolutional neural network (CNN) was developed from scratch and optimized specifically for real-time execution on embedded hardware. The model employs ReLU activation, Adam optimization, and a SoftMax output layer to enable efficient and accurate classification. The system employs a fixed-region segmentation strategy to prevent overcounting and utilizes GPIO-based control on a Raspberry Pi 5 to synchronize seed classification with physical sorting in real time. Seeds identified as defective are automatically removed via a servo-controlled ejection mechanism. The integrated system combines object detection, image processing, and real-time actuation, achieving a classification accuracy exceeding 99.6% and an average processing time of 12.4 milliseconds per seed. The proposed solution contributes to the industrial automation of pajuro sorting and provides a scalable framework for color-based grain classification applicable to a wide range of agricultural products. Full article

The ‘Annurca’ apple, an EU Protected Geographical Indication product, undergoes a mandatory post-harvest reddening in the ‘melaio’. This traditional practice enhances color and aroma but initiates detrimental textural degradation, creating a paradox where key quality attributes develop in conflict. This study aimed to characterize the sensory evolution of ‘Annurca’ apples during extended cold storage and its impact on consumer preference. A cohort of 551 untrained consumers evaluated the sensory profile at seven time points over a 221-day cold storage period. Multivariate data analyses were employed to identify preference drivers and define consumer segments. Consumer overall liking and market acceptability followed a significant non-linear, U-shaped trajectory, declining from an initial high (89.4% acceptability) to a minimum at day 159 (46.6% acceptability), before partially recovering. This trend inversely correlated with a peak in perceived mealiness, while hardness and crunchiness remained stable. Juiciness and aroma intensity were consistently identified as powerful positive liking drivers, whereas mealiness was the most significant and consistent negative driver. Sweetness’s importance as a preference driver significantly increased over storage time. Cluster analysis on highly rated samples revealed three distinct consumer preference profiles, challenging the traditional notion of a single ideal ‘Annurca’ apple. This study deconstructs the ‘melaio’ paradox, demonstrating that sensory evolution is a dynamic process defined by a trade-off between flavor development and textural decay. The findings provide a data-driven framework for optimizing the commercial strategy for this unique PGI cultivar, suggesting the need to mitigate mealiness and develop targeted marketing strategies for distinct consumer segments. Full article

Volatile compounds greatly affect tomato aroma, but systematic analysis of volatiles in tomatoes is limited by detection techniques. Here, HS-SPME Arrow-GC × GC-Q/TOFMS was employed to analyze tomato flavor profiles across different cultivation times. To investigate the effects of light and temperature on aroma profiles, three tomato samples across different cultivation periods, including S1 (harvested on May 30th, with lowest temperature and light conditions), S2 (harvested on August 10th, with the highest temperature and light), and S3 (harvested on June 27th, with moderate temperature and light), were analyzed. Overall, 227 volatiles were identified, belonging to 9 aroma categories. Hexanal, (E)-2-hexenal, nonanal, (E)-2-Octenal, trans-geranylacetone, 6-methyl-5-hepten-2-one, 3,4-Octadiene, 7-methyl-, and citral were found to be the key volatiles contributing most significantly to differentiating the samples across cultivation periods, imparting grassy and floral–fruity notes, respectively. The S1 tomatoes had a distinct grassy aroma, whereas the S3 tomatoes had a floral/fruity fragrance. Most differential metabolites were correlated with fatty acid, amino acid, and isoprenoid pathways. S1 tomatoes were characterized by fatty aldehydes (mainly C6/C9), and S2 tomatoes contained high concentrations of fatty alcohols. S3 tomatoes were positively correlated with isoprenoid-derived volatiles. These variations might be caused by the fluctuations in daily temperature and light intensity. This work establishes a foundational reference for assessing environmental effects on tomato flavor profiles. Full article

Background/Objectives: Soft tissues are essential for maintaining the function and long-term success of dental implants. In many cases, implant placement necessitates soft tissue augmentation procedures such as free gingival grafts (FGGs) or connective tissue grafts (CTGs) to restore lost gingival architecture. Nevertheless, a significant challenge associated with FGG and CTG is postoperative pain, largely due to morbidity at the palatal donor site. To address this issue, various approaches have been proposed to reduce patient discomfort and promote improved wound healing at the donor site. This study aimed to compare the effectiveness of four different methods for protecting the palatal donor site following free gingival graft harvesting. Methods: A total of 76 patients undergoing implant therapy with an indication for free gingival grafting were selected and divided into four groups based on the method used to protect the palatal donor site: an absorbable gelatin sponge secured with sutures (GS); an absorbable gelatin sponge with sutures and cyanoacrylate tissue adhesive (GS+CTA); oxidized regenerated cellulose combined with cyanoacrylate tissue adhesive (ORC+CTA); and an absorbable gelatin sponge covered with a flowable resin composite and stabilized with sutures (GS+FRC). The effectiveness of each method was evaluated in terms of postoperative pain, bleeding, and wound healing. Results: Although the differences in pain intensity among the groups were not statistically significant throughout the observation period (p > 0.05), the GS+FRC group consistently exhibited the lowest mean pain scores. No statistically significant differences were observed between the groups regarding the incidence of secondary bleeding. The highest mean wound healing rate was recorded in the GS+FRC group (75.95 ± 18.75%), whereas the ORC+CTA group demonstrated the lowest rate (43.66 ± 25.74%). Conclusions: The use of an absorbable gelatin sponge covered with a flowable resin composite and secured with sutures, despite the presented limitations, appears to be a promising approach for palatal wound protection. While this group consistently demonstrated the lowest mean pain scores, differences in pain intensity among the groups were not statistically significant. Nonetheless, it achieved the most favorable outcomes in terms of wound epithelialization. Full article

Accurate postharvest quality evaluation of soybeans is essential for preserving product value and meeting industry standards. Traditional inspection methods are often inconsistent, labor-intensive, and unsuitable for high-throughput operations. This study presents a non-destructive soybean classification approach using a simplified reflectance-mode hyperspectral imaging system equipped with a single light source, eliminating the complexity and maintenance demands of dual-light configurations used in prior studies. A spectral–spatial data fusion strategy was developed to classify harvested soybeans into four categories: normal, split, diseased, and foreign materials such as stems and pods. The dataset consisted of 1140 soybean samples distributed across these four categories, with spectral reflectance features and spatial texture attributes extracted from each sample. These features were combined to form a unified feature representation for use in classification. Among multiple machine learning classifiers evaluated, Linear Discriminant Analysis (LDA) achieved the highest performance, with approximately 99% accuracy, 99.05% precision, 99.03% recall and 99.03% F1-score. When evaluated independently, spectral features alone resulted in 98.93% accuracy, while spatial features achieved 78.81%, highlighting the benefit of the fusion strategy. Overall, this study demonstrates that a single-illumination HSI system, combined with spectral–spatial fusion and machine learning, offers a practical and potentially scalable approach for non-destructive soybean quality evaluation, with applicability in automated industrial processing environments. Full article

To improve the efficiency and reduce the cost of traditional sympodial bamboo harvesting, this study evaluated the effects of four harvesting intensities—selective harvesting, one-third clump, one-half clump, and complete clump harvesting—on understory plant diversity in pure Dendrocalamus giganteus stands over a five-year recovery period. A total of 36 species were recorded in the first year, increasing to 71 in the third year and stabilizing at 74 species by year five. Understory α-diversity showed an increasing trend followed by a decline. In the early recovery stage, species diversity was significantly correlated with soil chemical properties (p < 0.05), but no significant correlation was observed in the later stage. Fuzzy membership function analysis indicated that the 1/2 clump harvesting treatment outperformed others, ranking as follows: 1/2 clump > 1/3 clump > selective > complete clump harvesting. These results suggest that 1/2 clump harvesting is optimal for promoting understory vegetation growth, but its positive effects on biodiversity are time-limited, with the plant community showing a trend toward simplification over time. Full article

Fruit wines have become a popular alternative to grape wines for their variability of sensory properties and unique chemical profiles, offering interesting biological activities. Winemaking also utilizes fruits, which are usually sensitive to biological deterioration, thus reducing post-harvest losses. The quality of wines depends on the fermentation conditions, including the wine yeast selection. In this study, we observed the effect of three common Saccharomyces wine yeast strains on the physicochemical characteristics (color, pH, ethanol content), antioxidant potential (total polyphenol content—TPC, DPPH, and ABTS antioxidant assays), and sensory properties and their relations within plum, apple, and hawthorn wines. Generally, we observed quite-wide ranges in physicochemical properties (pH: 2.8–3.8, ethanol content: 9.0–16.2%) and antioxidant potential parameters (TPC: 0.5–2.4 mg/GAE, DPPH: 0.3–1.4 mg/AAE, 0.5–3.0 mg/AAE), which were affected by the fruit, yeast, and sampling term. The yeast strain significantly affected physicochemical properties and the antioxidant potential on a minor scale. The highest impact of yeast was observed within sensory analyses, where the hawthorn and apple wines fermented by yeast strain Fruit Red exhibited a different sensory profile than those fermented by the Buket and Special strains. A positive correlation between antioxidant potential parameters and their relationship with wine color was confirmed. Moreover, the overall acceptability grew with sweet taste intensity, and panelists preferred wines with lower ethanol content. In general, this study proved the significant impact of wine yeast strain selection on certain qualitative parameters of fruit wines. Full article

This study investigated the effects of light intensity regulation on yield and energy efficiency during potato pre-basic seed propagation in plant factories. Using virus-free ‘Favorita’ potato seedlings as experimental material, gradient light intensities (200, 300, and 400 μmol·m²·s⁻¹) were applied at four developmental stages: the seedling stage (SS), tuber formation stage (TFS), tuber growth stage (TGS), and harvest stage (HS), to explore the physiological mechanisms of stage-specific light intensity regulation and energy utilization efficiency. The results revealed that: (1) The per-plant tuber yield of the high yield group reached 72.91 g (T59 treatment), representing a 25% increase compared to the medium yield group and a 168% increase compared to the low yield group. Additionally, the high yield group exhibited superior leaf area, photosynthetic rate, and accumulation of sucrose and starch. (2) The impact of light intensity on tuber development exhibited stage specificity: low light intensity (200 μmol·m⁻²·s⁻¹) during TFS promoted early tuber initiation, while a high light intensity (400 μmol·m⁻²·s⁻¹) enhanced tuber formation efficiency. Increasing the light intensity during TGS facilitated the accumulation of sucrose and starch in tubers. (3) Energy use efficiency (EUE) increased significantly with yield, with the high yield group reaching 3.2 g MJ⁻¹, representing 52% and 88% improvements over the medium yield (2.1 g MJ⁻¹) and low yield (1.7 g MJ⁻¹) groups, respectively. A “stage-specific precision light supplementation” strategy was proposed, involving moderate light reduction (200 μmol·m⁻²·s⁻¹) during TFS and light enhancement (300 μmol·m⁻²·s⁻¹) during TGS to coordinate source-sink relationships and optimize carbohydrate metabolism. This study provides a theoretical basis for efficient potato production in plant factories. Full article

Plant pruning is the selective removal of specific plant parts to enhance growth, shape, and health. In this work, the effects of pruning were evaluated regarding the physiological parameters, maturity, quality, and harvest indices and the nutritional quality features of twelve chayote [Sechium edule (Jacq.) Sw] (Cucurbitaceae) varieties. GC-FID approaches were utilized to determine CO₂ assimilation rates. The results demonstrated that pruning upregulated the leaf temperature and conductance but decreased transpiration and CO₂ assimilation rates within the evaluated period (06:30 a.m.–16:23 p.m.). It was noted that the implementation of pruning also impacted samples with enhanced photosynthetically active radiation activity, with a positive correlation with CO₂ assimilation. The macro- and micronutrient content was higher in samples with an epidermis, especially for S. edule var. albus spinosum. Nevertheless, the analyzed samples presented low (5–10 mL CO₂ kg⁻¹ h⁻¹), medium (10–15 mL CO₂ kg⁻¹ h⁻¹), and high levels (15–20 mL CO₂ kg⁻¹ h⁻¹) of respiratory intensity and weight loss (7–17%)—effects attributed to botanical differences between the studied chayote varieties. This work demonstrates, for the first time, the effects of pruning in chayote orchards and expands the knowledge regarding the implementation of effective approaches to produce plants with culinary, cultural, and medicinal implications. Further approaches are required to determine the effects of pruning on chayote after harvest. Full article

Legg–Calvé–Perthes disease is a juvenile ischemic osteonecrosis (ON) of the femoral head. A disruption of blood supply to the femoral head produces extensive cell death and necrotic debris. Macrophages are innate immune cells recruited to the necrotic bone to orchestrate the repair process. However, the role macrophages play in the ON repair process is still not elucidated. The purpose of this study was to determine the effect of artificial necrotic bone fluid (NBF) on porcine peripheral blood mononuclear cell (PBMC)-derived macrophages. Monocytes were positively selected by CD14 MicroBeads from pig PBMCs. After maturation, cells were treated with no stimulant (Con), LPS + IFNγ (M1), IL4 + IL13 (M2), or NBF. All culture supernatants and cells were harvested for ELISA, Western blot, FACS, RT-qPCR and bulk RNAseq. The Western blot and ELISA showed that only the M1 condition elevated the protein level of pro-inflammatory cytokines. The FACS results indicated that percentage of CD8086+ (M1 marker) cells was significantly lower in the M2 vs. other conditions, whereas the relative median fluorescence intensity of CD8086 was significantly higher in the M1 vs. other conditions. The NBF did not show any significant change compared to the Con. mRNA analysis showed significantly increased IL1β and IL8 expression in the M1 vs. Con scenario. TNFα expression was significantly decreased in the M2 vs. Con scenario. Interestingly, the NBF did not induce pro-inflammatory gene expression. For bulk RNAseq, the Gene Set Enrichment Analyses of the M1-stimulated cells revealed the enrichment of pro-inflammatory gene sets. For the M2, most of the enriched categories were related to the down-regulation of inflammation. For the NBF, the most enriched categories were related to the down-regulation of protein translation and mitochondrial metabolism. We further confirmed the suppressive effects of NBF on macrophage functions using Seahorse Cell Mito Stress Tests, ¹³C-glucose metabolic flux analysis, mitochondrial ROS detection via MitoSOX^TM staining, and phagocytosis assay. Taken together, these results revealed that the artificial NBF down-regulates the overall cellular activity and energy metabolism of macrophages. Full article

The rapid development of artificial intelligence technologies has promoted the emergence of Agriculture 4.0, where the machines participating in agricultural activities are made smart with the capacities of self-sensing, self-decision-making, and self-execution. As representative implementations of Agriculture 4.0, intelligent selective fruit harvesting robots demonstrate significant potential to alleviate labor-intensive demands in modern agriculture, where visual detection serves as the foundational component. However, the accurate detection of fruits remains a challenging issue due to the complex and unstructured nature of fruit orchards. This paper comprehensively reviews the recent progress in visual detection methods for selective fruit harvesting robots, covering cameras, traditional detection based on handcrafted feature methods, detection based on deep learning methods, and tree branch detection methods. Furthermore, the potential challenges and future trends of the visual detection system of selective fruit harvesting robots are critically discussed, facilitating a thorough comprehension of contemporary progress in this research area. The primary objective of this work is to highlight the pivotal role of visual perception in intelligent fruit harvesting robots. Full article